Token
The basic unit of text that AI models process — roughly 3/4 of a word in English. 'Unbelievable' is 3 tokens. Token limits determine how much text a model can process at once.
Why it matters
Tokens are how AI usage is measured and priced, and how limits are enforced. This matters practically: pasting a huge document can exceed a model's capacity or run up costs, and "the AI forgot the start of our chat" usually means you hit a token limit. Knowing tokens exist helps you understand billing on API tools and why very long inputs sometimes get truncated.
A concrete example
The word "unbelievable" might split into pieces like "un," "believ," and "able," so it counts as several tokens, not one. A rough rule of thumb: 1,000 tokens is about 750 English words. So if a tool allows an 8,000-token input, you can fit roughly 6,000 words, a longish article, but not an entire book, before you'd need to trim or split it.
How to use it
As a rough planning figure, a thousand tokens is around 750 English words. That lets you sanity-check before you paste: a long report may not fit, and a loop that processes a thousand documents costs a thousand times one document. If you are paying per token, the cheapest optimisation is usually not a better model but sending less — trimming boilerplate, dropping the parts of a document that do not bear on the question.
The common mistake
Assuming token counts are the same across models and languages. Different tokenizers split text differently, and languages that are not English often need noticeably more tokens for the same content, which changes both cost and how much fits.
Related terms
Tokenizer
The component that splits text into tokens (sub-word units) before feeding it to an AI model. Different models use different tokenizers — affecting how they count input length, handle multilingual text, and process code.
Context Window
The maximum amount of text (measured in tokens) an AI model can consider at once. Larger context windows allow the model to reference more information in a single conversation.
Inference Cost
The computational expense of running a trained AI model to generate outputs. Measured in cost per token or per request. Varies dramatically between models — GPT-4 class models cost 10-50x more per token than smaller models.
Artificial Intelligence (AI)
The simulation of human intelligence by computer systems, including learning, reasoning, and self-correction. Modern AI is primarily powered by machine learning and neural networks.
Large Language Model (LLM)
An AI model trained on vast amounts of text data that can generate, summarize, translate, and analyze human language. Examples include the GPT, Claude, Gemini and Llama families.
Natural Language Processing (NLP)
The branch of AI focused on enabling computers to understand, interpret, and generate human language. Powers chatbots, translation, sentiment analysis, and text summarization.